Ensemble Classifiers for Steganalysis of Digital Media

TLDR

Steganalysis of digital media relies on supervised classifiers built from feature vectors, with support vector machines being the prevailing choice. This study proposes random‑forest ensemble classifiers as a superior alternative for steganalysis, enabling rapid detector construction with higher accuracy. Random forests offer lower training complexity, allowing steganalysts to use high‑dimensional cover models and larger training sets. The ensemble approach scales better with training size and feature dimensionality, matches SVM performance, and achieves markedly improved detection accuracy on three JPEG steganographic methods.

Abstract

Today, the most accurate steganalysis methods for digital media are built as supervised classifiers on feature vectors extracted from the media. The tool of choice for the machine learning seems to be the support vector machine (SVM). In this paper, we propose an alternative and well-known machine learning tool—ensemble classifiers implemented as random forests—and argue that they are ideally suited for steganalysis. Ensemble classifiers scale much more favorably w.r.t. the number of training examples and the feature dimensionality with performance comparable to the much more complex SVMs. The significantly lower training complexity opens up the possibility for the steganalyst to work with rich (high-dimensional) cover models and train on larger training sets—two key elements that appear necessary to reliably detect modern steganographic algorithms. Ensemble classification is portrayed here as a powerful developer tool that allows fast construction of steganography detectors with markedly improved detection accuracy across a wide range of embedding methods. The power of the proposed framework is demonstrated on three steganographic methods that hide messages in JPEG images.